HyperAIHyperAI초신경
홈플랫폼문서뉴스연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Command Palette

Search for a command to run...

Image Super Resolution On Set14 2X Upscaling

평가 지표

PSNR
SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper TitleRepository
DRCT-L35.360.9302DRCT: Saving Image Super-resolution away from Information Bottleneck
HMA†35.330.9297HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
HAT-L35.290.9293Activating More Pixels in Image Super-Resolution Transformer
Hi-IR-L35.270.9311Hierarchical Information Flow for Generalized Efficient Image Restoration-
HAT_FIR35.17-SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
HAT35.130.9282Activating More Pixels in Image Super-Resolution Transformer
CPAT+34.970.9280Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution-
DRCT34.960.9287DRCT: Saving Image Super-resolution away from Information Bottleneck
SwinFIR34.930.9276SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
CPAT34.910.9277Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution-
MaIR34.750.9268MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
DRLN+34.430.9247Densely Residual Laplacian Super-Resolution
CSRCNN34.340.9240Cascade Convolutional Neural Network for Image Super-Resolution-
LTE34.25-Local Texture Estimator for Implicit Representation Function
HAN+34.240.9224Single Image Super-Resolution via a Holistic Attention Network
CSNLN34.120.9223Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
DBPN-RES-MR64-334.090.921Deep Back-Projection Networks for Single Image Super-resolution
SwinOIR33.970.922Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy
SRFBN33.82-Feedback Network for Image Super-Resolution
HBPN33.780.921Hierarchical Back Projection Network for Image Super-Resolution
0 of 35 row(s) selected.